sniklaus/3d-ken-burns
an implementation of 3D Ken Burns Effect from a Single Image using PyTorch
Performs monocular depth estimation to reconstruct 3D geometry, then synthesizes novel camera trajectories with motion parallax effects using differentiable image warping implemented in CuPy CUDA kernels. Includes both an automated pipeline (`autozoom.py`) for one-shot video generation and an interactive web interface for manual camera path adjustment, with output to MP4 via MoviePy.
1,560 stars. No commits in the last 6 months.
Stars
1,560
Forks
224
Language
Python
License
—
Category
Last pushed
Jan 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/sniklaus/3d-ken-burns"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.